Publications

Prism: Dynamic and Flexible Benchmarking of LLMs Code Generation with Monte Carlo Tree Search
Vahid Majdinasab
Amin Nikanjam
Foutse Khomh
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Progressive Multi-Source Domain Adaptation for Personalized Facial Expression Recognition
Muhammad Osama Zeeshan
Marco Pedersoli
Alessandro Lameiras Koerich
Eric Grange
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Scaling Language-Free Visual Representation Learning
David Fan
Shengbang Tong
Jiachen Zhu
Koustuv Sinha
Zhuang Liu
Xinlei Chen
Michael G. Rabbat
Nicolas Ballas
Yann Lecun
Amir Bar
Saining Xie
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Sliced-Wasserstein Distance-based Data Selection
Julien Pallage
Antoine Lesage-Landry
We propose a new unsupervised anomaly detection method based on the sliced-Wasserstein distance for training data selection in machine learn… (voir plus)ing approaches. Our filtering technique is interesting for decision-making pipelines deploying machine learning models in critical sectors, e.g., power systems, as it offers a conservative data selection and an optimal transport interpretation. To ensure the scalability of our method, we provide two efficient approximations. The first approximation processes reduced-cardinality representations of the datasets concurrently. The second makes use of a computationally light Euclidian distance approximation. Additionally, we open the first dataset showcasing localized critical peak rebate demand response in a northern climate. We present the filtering patterns of our method on synthetic datasets and numerically benchmark our method for training data selection. Finally, we employ our method as part of a first forecasting benchmark for our open-source dataset.
2025-03-31
arXiv (publié)
doi.org
arxiv.org
TAPNext: Tracking Any Point (TAP) as Next Token Prediction
Artem Zholus
Carl Doersch
Yi Yang
Skanda Koppula
Viorica Patraucean
Xu Owen He
Ignacio Rocco
Mehdi S. M. Sajjadi
A. Chandar
Ross Goroshin
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Towards Assessing Deep Learning Test Input Generators
Seif Mzoughi
Ahmed Haj Yahmed
Mohamed Elshafei
Foutse Khomh
Diego Elias Costa
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Trade‐off of different deep learning‐based auto‐segmentation approaches for treatment planning of pediatric craniospinal irradiation autocontouring of OARs for pediatric CSI
Alana Thibodeau‐Antonacci
Marija Popovic
Ozgur Ates
Chia‐Ho Hua
James Schneider
Sonia Skamene
Carolyn Freeman
S. Enger
James Man Git Tsui
As auto‐segmentation tools become integral to radiotherapy, more commercial products emerge. However, they may not always suit our needs. … (voir plus)One notable example is the use of adult‐trained commercial software for the contouring of organs at risk (OARs) of pediatric patients.
2025-03-31
Medical Physics (Lancaster) (publié)
doi.org
View-Dependent Deformation Fields for 2D Editing of 3D Models
Martin El Mqirmi
Noam Aigerman
2025-03-31
arXiv (publié)
doi.org
arxiv.org
Why do LLMs attend to the first token?
Federico Barbero
'Alvaro Arroyo
Xiangming Gu
Christos Perivolaropoulos
Michael M. Bronstein
Petar Veličković
Razvan Pascanu
2025-03-31
arXiv (publié)
doi.org
arxiv.org
NoProp: Training Neural Networks without Back-propagation or Forward-propagation
Qinyu Li
Yee Whye Teh
Razvan Pascanu
2025-03-30
ArXiv (prépublication)
doi.org
arxiv.org
Universal algorithm for transforming Hamiltonian eigenvalues
Tatsuki Odake
Hlér Kristjánsson
Philip Taranto
Mio Murao
Manipulating Hamiltonians governing physical systems has found a broad range of applications, from quantum chemistry to semiconductor design… (voir plus). In this work, we provide a new way of manipulating Hamiltonians, by transforming their eigenvalues while keeping their eigenstates unchanged. We develop a universal algorithm that deterministically implements any desired (suitably differentiable) function on the eigenvalues of any unknown Hamiltonian, whose positive-time and negative-time dynamics are given as a black box. Our algorithm uses correlated randomness to efficiently combine two subroutines -- namely controlization and Fourier series simulation -- exemplifying a general compilation procedure that we develop. The time complexity of our algorithm is significantly reduced via said compilation technique compared to a na{ï}ve concatenation of the subroutines and outperforms similar methods based on the quantum singular value transformation.
2025-03-30
Physical Review Research (publié)
doi.org
arxiv.org
Steering CLIP's vision transformer with sparse autoencoders
Sonia Joseph
Praneet Suresh
Ethan Goldfarb
Lorenz Hufe
Yossi Gandelsman
Robert Graham
Danilo Bzdok
Wojciech Samek
Blake Aaron Richards
While vision models are highly capable, their internal mechanisms remain poorly understood-- a challenge which sparse autoencoders (SAEs) ha… (voir plus)ve helped address in language, but which remains underexplored in vision. We address this gap by training SAEs on CLIP's vision transformer and uncover key differences between vision and language processing, including distinct sparsity patterns for SAEs trained across layers and token types. We then provide the first systematic analysis of the steerability of CLIP's vision transformer by introducing metrics to quantify how precisely SAE features can be steered to affect the model's output. We find that 10-15% of neurons and features are steerable, with SAEs providing thousands more steerable features than the base model. Through targeted suppression of SAE features, we then demonstrate improved performance on three vision disentanglement tasks (CelebA, Waterbirds, and typographic attacks), finding optimal disentanglement in middle model layers, and achieving state-of-the-art performance on defense against typographic attacks. We release our CLIP SAE models and code to support future research in vision transformer interpretability.
2025-03-29
thecvf.com/CVPR/2025/Workshop/MIV (poster)
openreview.net
openreview.net